Search

The estimation of full body pose is a very difficult problem in Computer Vision. Due to high dimensionality of the pose space, it is challenging to search the true body configurations for any search strategy. In this chapter, we apply the stochastic Particle Swarm Optimization (PSO) algorithm to full body pose estimation problem. Our method fits an articulated body model to the volume data reconstructed from multiple camera images. Pose estimation is performed in a hierarchical manner with space constraints enforced into each sub-optimization step. To better address the dynamic pose tracking problem, the states of swarm particles are propagated according to a weak transition model. This maintains the diversity of particles and also utilizes the temporal continuity information. 3D distance transform is used for reducing the computing time of fitness evaluations. From the experiments, we demonstrate that by using PSO, our method can robustly fit the body model of a reference pose to the beginning frame, and can track fast human movements in multiple image sequences. [ABSTRACT FROM AUTHOR]

In order to achieve precise, accurate and reliable tracking of human movement, a 3D human model that is very similar to the subject is essential. In this paper, we present a new system to (1) precisely construct the surface shape of the whole human body, and (2) estimate the underlying skeleton. In this work we make use of a set of images of the subject in collaboration with a generic anthropometrical 3D model made up of regular surfaces and skeletons to adapt to the specific subject. We developed a three-stage technique that uses the human shape feature points and limb outlines that work together with the generic 3D model to yield our final customized 3D model. The first stage is an iterative camera pose calibration and 3D characteristic point reconstruction-deformation algorithm that gives us an initial customized 3D model. The second stage refines the initial customized 3D model by deformation via the silhouette limbs information, thus obtaining the surface skin model. In the final stage, we make use of the results of skin deformation to estimate the underlying skeleton. From our final results, we demonstrate that our system is able to construct quality human model, where the skeleton is constructed and positioned automatically. [ABSTRACT FROM AUTHOR]